•A dam deformation spatiotemporal hybrid model considering chaotic effect in residual series is proposed.•The model has good ability to predict the overall deformation simultaneously.•Effective components contained in residual series are extracted by PSO-SVM model. Single-measuring point deformation monitoring model is the most popular method in dam health monitoring. Considering that single-point monitoring model cannot comprehensively reflect the overall deformation properties of dams, a spatiotemporal hybrid model of multi-point deformation monitoring for concrete arch dams is proposed. Meanwhile, considering the chaotic effect of residual series, the support vector machine optimized by particle swarm optimization algorithm (PSO-SVM) is adopted to analyze and forecast the residual series. Hence, a spatiotemporal hybrid model for concrete arch dam deformation monitoring considering the chaotic effect of residual series is proposed in the study. Based on the theory of single-measuring point deformation monitoring, a spatiotemporal hybrid model is established by introducing space coordinate and calculating hydraulic component with finite element method. Then, with the good nonlinear processing ability of PSO-SVM, the chaotic effect of residual series is analyzed and predicted by PSO-SVM. Subsequently, a spatiotemporal hybrid model for concrete arch dam deformation monitoring considering chaotic effect of residual series is established by superimposing the residual prediction term with the predicted value of the spatiotemporal hybrid model. Engineering example show that the proposed model has better fitting and predicting precisions compared with the conventional single-point monitoring models, and it can analyze and predict the deformations of multi-point simultaneously. In addition, the proposed model reduces the workload of modelling point by point in single-point monitoring model, which considerably improves the practicality and computational efficiency of deformation-based health monitoring of concrete arch dams.